Paper Info
Title
Interactively building a discriminative vocabulary of nameable attributes
Abstract
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be inefficient (costing substantial effort or expertise) and/or insufficient (descriptive properties need not be discriminative). We introduce an approach to define a vocabulary of attributes that is both human understandable and discriminative. The system takes object/scene-labeled images as input, and returns as output a set of attributes elicited from human annotators that distinguish the categories of interest. To ensure a compact vocabulary and efficient use of annotators' effort, we 1) show how to actively augment the vocabulary such that new attributes resolve inter-class confusions, and 2) propose a novel “nameability” manifold that prioritizes candidate attributes by their likelihood of being associated with a nameable property. We demonstrate the approach with multiple datasets, and show its clear advantages over baselines that lack a nameability model or rely on a list of expert-provided attributes.
Year
DOI
Venue
2011
10.1109/CVPR.2011.5995451
Computer Vision and Pattern Recognition
Keywords
Field
DocType
object recognition,substantial effort,expert-provided attribute,nameability model,human-nameable visual attribute,discriminative vocabulary,efficient use,clear advantage,descriptive property,human annotators,compact vocabulary,nameable attribute,visualization,manifolds,support vector machines
Computer vision,Pattern recognition,Computer science,Baseline (configuration management),Artificial intelligence,Activity-based costing,Vocabulary,Discriminative model,Cognitive neuroscience of visual object recognition
Conference
Volume
Issue
ISSN
2011
1
1063-6919
ISBN
Citations 
PageRank 
978-1-4577-0394-2
118
4.21
References 
Authors
25
2
Search Limit
100118
Name
Order
Citations
PageRank
Devi Parikh12929132.01
Kristen Grauman26258326.34